Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    list element assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.95
     vortices
    0.78
    iert
    0.73
    sellers
    0.73
     pox
    0.71
    triangleleft
    0.70
     dimers
    0.70
    ्य
    0.67
     republics
    0.66
    sons
    0.66
    POSITIVE LOGITS
    ist
    0.95
    ية
    0.89
    ﮕ
    0.83
     telepon
    0.80
     egli
    0.79
    おり
    0.78
    ﺓ
    0.78
    μα
    0.77
    ﻟ
    0.77
     econ
    0.75
    Act Density 0.015%

    No Known Activations